Authors:
Karam Abdullah
1
;
2
;
Imen Jegham
3
;
4
;
Mohamed Mahjoub
3
and
Anouar Ben Khalifa
3
;
5
Affiliations:
1
Université de Sousse, ISITCom, LATIS-Laboratory of Advanced Technology and Intelligent Systems, 4011, Sousse, Tunisia
;
2
University of Mosul, Collage of Education for Pure Science, Computer Science Department, Mosul, Iraq
;
3
Université de Sousse, Ecole Nationale d’Ingénieurs de Sousse, LATIS- Laboratory of Advanced Technology and Intelligent Systems, 4023, Sousse, Tunisia
;
4
Horizon School of Digital Technologies, 4023, Sousse, Tunisia
;
5
Université de Jendouba, Institut National des Technologies et des Sciences du Kef, 7100, Le Kef, Tunisia
Keyword(s):
Driver Action Recognition, Driving at Nighttime, Deep Learning, Hard Attention, Spatial Attention.
Abstract:
Driver monitoring has become a key challenge in both computer vision and intelligent transportation system research fields due to its high potential to save pedestrians, drivers, and passengers’ lives. In fact, a variety of issues related to driver action classification in real-world driving settings are present and make classification a challenging task. Recently, driver in-vehicle action relying on deep neural networks has made significant progress. Though promising classification results have been achieved in the daytime, the performance in the nighttime remains far from satisfactory. In addition, deep learning techniques treat the whole input data with the same importance which is confusing. In this work, a nighttime driver action classification network called hard spatial attention is proposed. Our approach effectively captures the relevant dynamic spatial information of the cluttered driving scenes under low illumination for an efficient driver action classification. Experiment
s are performed on the unique public realistic driver action dataset recorded at nighttime 3MDAD dataset. Our approach outperforms state-of-the-art methods’ classification accuracies on both side and front views.
(More)